Update README.md

README.md

@@ -1,3 +1,30 @@
 ---
 license: apache-2.0
----
+datasets:
+- spider
+metrics:
+- accuracy
+model-index:
+- name: lever-spider-codex
+  results:
+  - task:
+      type: code generation             # Required. Example: automatic-speech-recognition
+      # name: {task_name}             # Optional. Example: Speech Recognition
+    dataset:
+      type: spider          # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
+      name: spider (text-to-sql)          # Required. A pretty name for the dataset. Example: Common Voice (French)
+      # config: {dataset_config}      # Optional. The name of the dataset configuration used in `load_dataset()`. Example: fr in `load_dataset("common_voice", "fr")`. See the `datasets` docs for more info: https://huggingface.co/docs/datasets/package_reference/loading_methods#datasets.load_dataset.name
+      # split: {dataset_split}        # Optional. Example: test
+      # revision: {dataset_revision}  # Optional. Example: 5503434ddd753f426f4b38109466949a1217c2bb
+      # args:
+      #   {arg_0}: {value_0}          # Optional. Additional arguments to `load_dataset()`. Example for wikipedia: language: en
+      #   {arg_1}: {value_1}          # Optional. Example for wikipedia: date: 20220301
+    metrics:
+      - type: accuracy         # Required. Example: wer. Use metric id from https://hf.co/metrics
+        value: 81.9       # Required. Example: 20.90
+        # name: {metric_name}         # Optional. Example: Test WER
+        # config: {metric_config}     # Optional. The name of the metric configuration used in `load_metric()`. Example: bleurt-large-512 in `load_metric("bleurt", "bleurt-large-512")`. See the `datasets` docs for more info: https://huggingface.co/docs/datasets/v2.1.0/en/loading#load-configurations
+        # args:
+        #   {arg_0}: {value_0}        # Optional. The arguments passed during `Metric.compute()`. Example for `bleu`: max_order: 4
+        verified: false              # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).
+---